Open A-Specker opened 5 years ago
replace with m = cv2.estimateAffinePartial2D(prev_pts, curr_pts)[0]
File "Stabilize.py", line 93 m = cv2.estimateAffinePartial2D(prev_pts, curr_pts)[0] ^ IndentationError: unindent does not match any outer indentation level
File "Stabilize.py", line 93 m = cv2.estimateAffinePartial2D(prev_pts, curr_pts)[0] ^ IndentationError: unindent does not match any outer indentation level
IntendationError, Worked now, thank you
435
height 1280
height 720
1196444237
Traceback (most recent call last):
File "Stabilize.py", line 147, in
fix with frame_out = cv2.resize(frame_out, (int(frame_out.shape[1]/2), int(frame_out.shape[0]/2)));
I tried the above and got this error:
Exception has occurred: error
OpenCV(4.4.0) C:\Users\appveyor\AppData\Local\Temp\1\pip-req-build-6lylwdcz\opencv\modules\calib3d\src\ptsetreg.cpp:174: error: (-215:Assertion failed) count >= 0 && count2 == count in function 'cv::RANSACPointSetRegistrator::run'
File "C:\...\video_stabilization.py", line 96, in <module>
m = cv2.estimateAffinePartial2D(prev_pts, curr_pts)[0]
Wonder how does this work on a live stream? because there is no an entire video worth of frames to compare
https://github.com/krutikabapat/Video-Stabilization-using-OpenCV/blob/36581dcb243c6364559235b2eed385c812eeb152/video_stabilization.py#L92
The function estimateRigidTransform is deprecated in version 4 and the could won't work. Would be cool if you fix it.